Member of Technical Staff — RL Research (Experienced)

Location: In-person in Seattle, five days a week

Salary: $300,000–$500,000 annual base salary, plus equity

Company

hirify.global is building photorealistic, real-time AI avatars with emotional intelligence through full-duplex audiovisual foundation models.

What you will do

• Build Nuance’s RL and post-training stack from 0→1 and scale it from 1→10.
• Develop rollout generation, policy optimization, reward and reference model serving, evaluation, checkpointing, observability, and debugging systems.
• Design abstractions connecting research ideas with production-scale trainers, rollout workers, evaluators, data queues, experience buffers, and checkpoint promotion.
• Develop feedback loops for turn-taking, interruption, timing, emotional response, audiovisual coherence, instruction following, and real-time interaction quality.
• Optimize rollout throughput, serving latency, GPU utilization, policy updates, queueing, checkpoint overhead, and research iteration speed.

Requirements

• Significant hands-on experience with RL, RLHF, RLAIF, post-training, alignment, or large-scale fine-tuning for foundation models.
• Deep understanding of policy optimization, reward modeling, preference optimization, rejection sampling, KL control, evaluation, and data feedback loops.
• Experience reasoning about reward hacking, unstable rewards, distribution shift, stale policies, mode collapse, over-optimization, noisy preferences, and evaluation mismatch.
• Experience building or operating RL and post-training pipelines at scale with verl, ms-swift, OpenRLHF, equivalent systems, or rollout serving systems such as vLLM.
• Experience with large-scale training or inference systems, including serving, batching, queueing, GPU utilization, checkpointing, and debugging.
• Understanding of multimodal post-training for real-time audio-video-language interaction and strong software engineering fundamentals.

Nice to have

• Experience building post-training systems, RL pipelines, agent training systems, evaluation platforms, or model improvement loops from 0→1.
• Experience with PPO, GRPO, DPO, online RL, reward modeling, preference data, synthetic data generation, or model-based data improvement.
• Experience with multimodal, long-context, or real-time interactive systems and mixed training/inference workloads across large GPU clusters.
• Publications or substantial open-source contributions in RL, post-training, alignment, evaluation, ML systems, or model behavior.

Culture & Benefits

• Visa sponsorship is available from day one, including O-1, H-1B, and green card support.
• HSA health plan with approximately $2,000 in annual company contributions.
• 15 days of PTO, public holidays, and a full week of office closure at year-end.
• Weekday lunch, drinks, and snacks provided.
• Commuter benefits and a 401(k) plan.
• AI-native tooling with unlimited tokens.